1 Version
V2.1
2 Functions
- Receives the Spherical Harmonic Decomposition coefficients of the sound field
- Detects and directions of active sound sources (ither be a speech or a non-speech signal) and to separate them.
- Produces the Transformed Speech and Audio Scene Geometry..
3 Reference Model
4 Input/Output Data
Input data | Semantics |
Spherical Harmonics Decomposition Coefficients | Result of the transformation of Transform Multichannel Audio into the spherical frequency domain. |
Source Model KB info | Discrete-time and discrete-valued simple acoustic source models used in source separation. |
Output data | Semantics |
Transform Audio | |
Audio Scene Geometry |
5 SubAIMs
No SubAIMs.
6 JSON Metadata
https://schemas.mpai.community/CAE/V2.1/AIMs/SpeechDetectionandSeparation.json